Abstract
In this paper, we propose a new geometric model based on mixture of Markov Random Fields (MRFs) for human pose estimation. We build on previous work that expresses the global constraints on the relative locations of the body joints using an auto-encoder ConvNet which performs dimensionality reduction on the heat maps, and recovers in this manner a low dimensional manifold on which the global pose of the human body lies. To address the shortcomings of this architecture, and obtain more meaningful vectors that span the low dimensional pose space, we propose to replace the auto-encoder network layer with a layer that implements a Gaussian mixture model (GMM) that provides a soft clustering of the human pose predictions in an online fashion. We show that: (a) a large number of meaningful global poses is feasible, this way preserving the underlying structure of informative body poses; (b) the clustering helps to properly initialize the MRF filters of each different global pose, (c) a body joint masking data augmentation procedure can be better exploited and that (d) the system stability is significantly improved. To the best of our knowledge, this is the first time that a clustering algorithm like GMM is used in an online fashion for the problem of 2D human pose estimation. The efficacy of our framework has been demonstrated through extensive experiments on widely used public benchmarks.
I. Marras and P. Palasek—This work was done while the authors were at Queen Mary University of London.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andriluka, M., Pishchulin, L., Gehler, P., Bernt, S.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR, pp. 3686–3693, June 2014
Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035. Society for Industrial and Applied Mathematics (2007)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Bulat, A., Tzimiropoulos, G.: Human pose estimation via convolutional part heatmap regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 717–732. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_44
Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human pose estimation with iterative error feedback. In: CVPR, pp. 4733–4742 (2016)
Chen, X., Yuille, A.L.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: NIPS, pp. 1736–1744 (2014)
Chen, Y., Shen, C., Wei, X., Liu, L., Yang, J.: Adversarial PoseNet: a structure-aware convolutional network for human pose estimation. In: ICCV, pp. 1212–1221 (2017)
Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: CVPR, pp. 1831–1840 (2017)
Dantone, M., Gall, J., Leistner, C., Van Gool, L.: Body parts dependent joint regressors for human pose estimation in still images. PAMI 36, 2131–2143 (2014)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodol.) 39, 1–38 (1977)
Dilokthanakul, N., et al.: Deep unsupervised clustering with Gaussian mixture variational autoencoders. arXiv preprint arXiv:1611.02648 (2016)
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. JMLR 12, 2121–2159 (2011)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1–8 (2008)
Gkioxari, G., Arbeláez, P., Bourdev, L., Malik, J.: Articulated pose estimation using discriminative armlet classifiers. In: CVPR, pp. 3342–3349 (2013)
Gkioxari, G., Toshev, A., Jaitly, N.: Chained predictions using convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 728–743. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_44
Güler, R., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: CVPR (2018)
Hu, P., Ramanan, D.: Bottom-up and top-down reasoning with convolutional latent-variable models. In: CVPR, pp. 5600–5609 (2016)
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34–50. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_3
Jain, A., Tompson, J., LeCun, Y., Bregler, C.: MoDeep: a deep learning framework using motion features for human pose estimation. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 302–315. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16808-1_21
Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, pp. 12.1–12.11 (2010)
Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: CVPR, pp. 1465–1472 (2011)
Ke, L., Chang, M.-C., Qi, H., Lyu, S.: Multi-scale structure-aware network for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 731–746. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_44
Krapac, J., Verbeek, J., Jurie, F.: Modeling spatial layout with Fisher vectors for image categorization. In: ICCV, pp. 1487–1494. IEEE (2011)
Lifshitz, I., Fetaya, E., Ullman, S.: Human pose estimation using deep consensus voting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 246–260. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_16
Luvizon, D.C., Tabia, H., Picard, D.: Human pose regression by combining indirect part detection and contextual information. CoRR (2017)
Marras, I., Palasek, P., Patras, I.: Deep globally constrained MRFs for human pose estimation. In: ICCV, pp. 3466–3475 (2017)
Neal, R.M., Hinton, G.E.: A view of the EM algorithm that justifies incremental, sparse, and other variants. In: Jordan, M.I. (ed.) Learning in Graphical Models, pp. 355–368. Springer, Dordrecht (1998). https://doi.org/10.1007/978-94-011-5014-9_12
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Nie, X., Feng, J., Zuo, Y., Yan, S.: Human pose estimation with parsing induced learner. In: CVPR, pp. 2100–2108 (2018)
Palasek, P., Patras, I.: Discriminative convolutional Fisher vector network for action recognition. arXiv preprint arXiv:1707.06119 (2017)
Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: adversarial data augmentation in human pose estimation. In: CVPR, pp. 2226–2234 (2018)
Pfister, T., Simonyan, K., Charles, J., Zisserman, A.: Deep convolutional neural networks for efficient pose estimation in gesture videos. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 538–552. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16865-4_35
Pishchulin, L., et al.: Deepcut: joint subset partition and labeling for multi person pose estimation. In: CVPR, pp. 4929–4937 (2016)
Sapp, B., Taskar, B.: Modec: multimodal decomposable models for human pose estimation. In: CVPR, pp. 3674–3681 (2013)
Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26–31 (2012)
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR, pp. 648–656 (2015)
Tompson, J., Jain, A., LeCun, Y., Bregler, C.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS, pp. 1799–1807 (2014)
Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: CVPR, pp. 1653–1660 (2014)
Tüske, Z., Tahir, M.A., Schlüter, R., Ney, H.: Integrating Gaussian mixtures into deep neural networks: softmax layer with hidden variables. In: ICASSP, pp. 4285–4289 (2015)
Variani, E., McDermott, E., Heigold, G.: A Gaussian mixture model layer jointly optimized with discriminative features within a deep neural network architecture. In: ICASSP, pp. 4270–4274 (2015)
Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR, pp. 4724–4732 (2016)
Yang, Y., Ramanan, D.: Articulated human detection with flexible mixtures of parts. PAMI 35(12), 2878–2890 (2013)
Zong, B., et al.: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In: ICLR (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Marras, I., Palasek, P., Patras, I. (2019). Deep Mixture of MRFs for Human Pose Estimation. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11363. Springer, Cham. https://doi.org/10.1007/978-3-030-20893-6_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-20893-6_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20892-9
Online ISBN: 978-3-030-20893-6
eBook Packages: Computer ScienceComputer Science (R0)